graphics

finitearth · finitearth · commit 69952178bae7 · 2024-09-26T12:26:23.000+02:00
diff --git a/notebooks/evaluation_experiment.ipynb b/notebooks/evaluation_experiment.ipynb
@@ -10,7 +10,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -24,7 +24,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -61,7 +61,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -183,7 +183,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -195,7 +195,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -209,7 +209,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -219,7 +219,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -244,7 +244,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -266,7 +266,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -288,7 +288,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -468,7 +468,7 @@
        "init        Llama-3-70B    init      False          53.17 ± 17.86  "
       ]
      },
-     "execution_count": 42,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -496,7 +496,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 76,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -509,7 +509,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 85,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -521,7 +521,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 86,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
@@ -669,7 +669,7 @@
        "                                    True            64.33 ± 2.25  "
       ]
      },
-     "execution_count": 86,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -682,7 +682,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 87,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [
     {
@@ -704,7 +704,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 88,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
@@ -733,7 +733,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -747,7 +747,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -762,7 +762,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [
     {
@@ -783,7 +783,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [
     {
@@ -883,7 +883,7 @@
        "            gpt-4o         DE        False          51.33 ± 1.53  69.50 ± 2.60  "
       ]
      },
-     "execution_count": 51,
+     "execution_count": 19,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -902,7 +902,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 62,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [
     {
@@ -929,7 +929,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 63,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [
     {
@@ -1043,7 +1043,7 @@
        "                           GA        False          68.83 ± 8.75  67.83 ± 5.77  "
       ]
      },
-     "execution_count": 63,
+     "execution_count": 21,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1055,7 +1055,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 64,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [
     {
@@ -1082,7 +1082,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 65,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [
     {
@@ -1196,7 +1196,7 @@
        "                          GA        False          63.67 ± 10.05  "
       ]
      },
-     "execution_count": 65,
+     "execution_count": 23,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1215,7 +1215,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1231,7 +1231,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [
     {
@@ -1252,7 +1252,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": 26,
    "metadata": {},
    "outputs": [
     {
@@ -1346,7 +1346,7 @@
        "init        gpt-4o         init      False          57.17 ± 12.10  "
       ]
      },
-     "execution_count": 54,
+     "execution_count": 26,
      "metadata": {},
      "output_type": "execute_result"
     }

Original file line number	Diff line number	Diff line change
`@@ -10,7 +10,7 @@`
`10`	`10`	`},`
`11`	`11`	`{`
`12`	`12`	`"cell_type": "code",`
`13`		`- "execution_count": 33,`
	`13`	`+ "execution_count": 1,`
`14`	`14`	`"metadata": {},`
`15`	`15`	`"outputs": [],`
`16`	`16`	`"source": [`
`@@ -24,7 +24,7 @@`
`24`	`24`	`},`
`25`	`25`	`{`
`26`	`26`	`"cell_type": "code",`
`27`		`- "execution_count": 34,`
	`27`	`+ "execution_count": 2,`
`28`	`28`	`"metadata": {},`
`29`	`29`	`"outputs": [],`
`30`	`30`	`"source": [`
`@@ -61,7 +61,7 @@`
`61`	`61`	`},`
`62`	`62`	`{`
`63`	`63`	`"cell_type": "code",`
`64`		`- "execution_count": 35,`
	`64`	`+ "execution_count": 3,`
`65`	`65`	`"metadata": {},`
`66`	`66`	`"outputs": [],`
`67`	`67`	`"source": [`
`@@ -183,7 +183,7 @@`
`183`	`183`	`},`
`184`	`184`	`{`
`185`	`185`	`"cell_type": "code",`
`186`		`- "execution_count": 36,`
	`186`	`+ "execution_count": 4,`
`187`	`187`	`"metadata": {},`
`188`	`188`	`"outputs": [],`
`189`	`189`	`"source": [`
`@@ -195,7 +195,7 @@`
`195`	`195`	`},`
`196`	`196`	`{`
`197`	`197`	`"cell_type": "code",`
`198`		`- "execution_count": 37,`
	`198`	`+ "execution_count": 5,`
`199`	`199`	`"metadata": {},`
`200`	`200`	`"outputs": [],`
`201`	`201`	`"source": [`
`@@ -209,7 +209,7 @@`
`209`	`209`	`},`
`210`	`210`	`{`
`211`	`211`	`"cell_type": "code",`
`212`		`- "execution_count": 38,`
	`212`	`+ "execution_count": 6,`
`213`	`213`	`"metadata": {},`
`214`	`214`	`"outputs": [],`
`215`	`215`	`"source": [`
`@@ -219,7 +219,7 @@`
`219`	`219`	`},`
`220`	`220`	`{`
`221`	`221`	`"cell_type": "code",`
`222`		`- "execution_count": 39,`
	`222`	`+ "execution_count": 7,`
`223`	`223`	`"metadata": {},`
`224`	`224`	`"outputs": [`
`225`	`225`	`{`
`@@ -244,7 +244,7 @@`
`244`	`244`	`},`
`245`	`245`	`{`
`246`	`246`	`"cell_type": "code",`
`247`		`- "execution_count": 40,`
	`247`	`+ "execution_count": 8,`
`248`	`248`	`"metadata": {},`
`249`	`249`	`"outputs": [`
`250`	`250`	`{`
`@@ -266,7 +266,7 @@`
`266`	`266`	`},`
`267`	`267`	`{`
`268`	`268`	`"cell_type": "code",`
`269`		`- "execution_count": 41,`
	`269`	`+ "execution_count": 9,`
`270`	`270`	`"metadata": {},`
`271`	`271`	`"outputs": [`
`272`	`272`	`{`
`@@ -288,7 +288,7 @@`
`288`	`288`	`},`
`289`	`289`	`{`
`290`	`290`	`"cell_type": "code",`
`291`		`- "execution_count": 42,`
	`291`	`+ "execution_count": 10,`
`292`	`292`	`"metadata": {},`
`293`	`293`	`"outputs": [`
`294`	`294`	`{`
`@@ -468,7 +468,7 @@`
`468`	`468`	`"init Llama-3-70B init False 53.17 ± 17.86 "`
`469`	`469`	`]`
`470`	`470`	`},`
`471`		`- "execution_count": 42,`
	`471`	`+ "execution_count": 10,`
`472`	`472`	`"metadata": {},`
`473`	`473`	`"output_type": "execute_result"`
`474`	`474`	`}`
`@@ -496,7 +496,7 @@`
`496`	`496`	`},`
`497`	`497`	`{`
`498`	`498`	`"cell_type": "code",`
`499`		`- "execution_count": 76,`
	`499`	`+ "execution_count": 11,`
`500`	`500`	`"metadata": {},`
`501`	`501`	`"outputs": [],`
`502`	`502`	`"source": [`
`@@ -509,7 +509,7 @@`
`509`	`509`	`},`
`510`	`510`	`{`
`511`	`511`	`"cell_type": "code",`
`512`		`- "execution_count": 85,`
	`512`	`+ "execution_count": 12,`
`513`	`513`	`"metadata": {},`
`514`	`514`	`"outputs": [],`
`515`	`515`	`"source": [`
`@@ -521,7 +521,7 @@`
`521`	`521`	`},`
`522`	`522`	`{`
`523`	`523`	`"cell_type": "code",`
`524`		`- "execution_count": 86,`
	`524`	`+ "execution_count": 13,`
`525`	`525`	`"metadata": {},`
`526`	`526`	`"outputs": [`
`527`	`527`	`{`
`@@ -669,7 +669,7 @@`
`669`	`669`	`" True 64.33 ± 2.25 "`
`670`	`670`	`]`
`671`	`671`	`},`
`672`		`- "execution_count": 86,`
	`672`	`+ "execution_count": 13,`
`673`	`673`	`"metadata": {},`
`674`	`674`	`"output_type": "execute_result"`
`675`	`675`	`}`
`@@ -682,7 +682,7 @@`
`682`	`682`	`},`
`683`	`683`	`{`
`684`	`684`	`"cell_type": "code",`
`685`		`- "execution_count": 87,`
	`685`	`+ "execution_count": 14,`
`686`	`686`	`"metadata": {},`
`687`	`687`	`"outputs": [`
`688`	`688`	`{`
`@@ -704,7 +704,7 @@`
`704`	`704`	`},`
`705`	`705`	`{`
`706`	`706`	`"cell_type": "code",`
`707`		`- "execution_count": 88,`
	`707`	`+ "execution_count": 15,`
`708`	`708`	`"metadata": {},`
`709`	`709`	`"outputs": [`
`710`	`710`	`{`
`@@ -733,7 +733,7 @@`
`733`	`733`	`},`
`734`	`734`	`{`
`735`	`735`	`"cell_type": "code",`
`736`		`- "execution_count": 48,`
	`736`	`+ "execution_count": 16,`
`737`	`737`	`"metadata": {},`
`738`	`738`	`"outputs": [],`
`739`	`739`	`"source": [`
`@@ -747,7 +747,7 @@`
`747`	`747`	`},`
`748`	`748`	`{`
`749`	`749`	`"cell_type": "code",`
`750`		`- "execution_count": 49,`
	`750`	`+ "execution_count": 17,`
`751`	`751`	`"metadata": {},`
`752`	`752`	`"outputs": [],`
`753`	`753`	`"source": [`
`@@ -762,7 +762,7 @@`
`762`	`762`	`},`
`763`	`763`	`{`
`764`	`764`	`"cell_type": "code",`
`765`		`- "execution_count": 50,`
	`765`	`+ "execution_count": 18,`
`766`	`766`	`"metadata": {},`
`767`	`767`	`"outputs": [`
`768`	`768`	`{`
`@@ -783,7 +783,7 @@`
`783`	`783`	`},`
`784`	`784`	`{`
`785`	`785`	`"cell_type": "code",`
`786`		`- "execution_count": 51,`
	`786`	`+ "execution_count": 19,`
`787`	`787`	`"metadata": {},`
`788`	`788`	`"outputs": [`
`789`	`789`	`{`
`@@ -883,7 +883,7 @@`
`883`	`883`	`" gpt-4o DE False 51.33 ± 1.53 69.50 ± 2.60 "`
`884`	`884`	`]`
`885`	`885`	`},`
`886`		`- "execution_count": 51,`
	`886`	`+ "execution_count": 19,`
`887`	`887`	`"metadata": {},`
`888`	`888`	`"output_type": "execute_result"`
`889`	`889`	`}`
`@@ -902,7 +902,7 @@`
`902`	`902`	`},`
`903`	`903`	`{`
`904`	`904`	`"cell_type": "code",`
`905`		`- "execution_count": 62,`
	`905`	`+ "execution_count": 20,`
`906`	`906`	`"metadata": {},`
`907`	`907`	`"outputs": [`
`908`	`908`	`{`
`@@ -929,7 +929,7 @@`
`929`	`929`	`},`
`930`	`930`	`{`
`931`	`931`	`"cell_type": "code",`
`932`		`- "execution_count": 63,`
	`932`	`+ "execution_count": 21,`
`933`	`933`	`"metadata": {},`
`934`	`934`	`"outputs": [`
`935`	`935`	`{`
`@@ -1043,7 +1043,7 @@`
`1043`	`1043`	`" GA False 68.83 ± 8.75 67.83 ± 5.77 "`
`1044`	`1044`	`]`
`1045`	`1045`	`},`
`1046`		`- "execution_count": 63,`
	`1046`	`+ "execution_count": 21,`
`1047`	`1047`	`"metadata": {},`
`1048`	`1048`	`"output_type": "execute_result"`
`1049`	`1049`	`}`
`@@ -1055,7 +1055,7 @@`
`1055`	`1055`	`},`
`1056`	`1056`	`{`
`1057`	`1057`	`"cell_type": "code",`
`1058`		`- "execution_count": 64,`
	`1058`	`+ "execution_count": 22,`
`1059`	`1059`	`"metadata": {},`
`1060`	`1060`	`"outputs": [`
`1061`	`1061`	`{`
`@@ -1082,7 +1082,7 @@`
`1082`	`1082`	`},`
`1083`	`1083`	`{`
`1084`	`1084`	`"cell_type": "code",`
`1085`		`- "execution_count": 65,`
	`1085`	`+ "execution_count": 23,`
`1086`	`1086`	`"metadata": {},`
`1087`	`1087`	`"outputs": [`
`1088`	`1088`	`{`
`@@ -1196,7 +1196,7 @@`
`1196`	`1196`	`" GA False 63.67 ± 10.05 "`
`1197`	`1197`	`]`
`1198`	`1198`	`},`
`1199`		`- "execution_count": 65,`
	`1199`	`+ "execution_count": 23,`
`1200`	`1200`	`"metadata": {},`
`1201`	`1201`	`"output_type": "execute_result"`
`1202`	`1202`	`}`
`@@ -1215,7 +1215,7 @@`
`1215`	`1215`	`},`
`1216`	`1216`	`{`
`1217`	`1217`	`"cell_type": "code",`
`1218`		`- "execution_count": 52,`
	`1218`	`+ "execution_count": 24,`
`1219`	`1219`	`"metadata": {},`
`1220`	`1220`	`"outputs": [],`
`1221`	`1221`	`"source": [`
`@@ -1231,7 +1231,7 @@`
`1231`	`1231`	`},`
`1232`	`1232`	`{`
`1233`	`1233`	`"cell_type": "code",`
`1234`		`- "execution_count": 53,`
	`1234`	`+ "execution_count": 25,`
`1235`	`1235`	`"metadata": {},`
`1236`	`1236`	`"outputs": [`
`1237`	`1237`	`{`
`@@ -1252,7 +1252,7 @@`
`1252`	`1252`	`},`
`1253`	`1253`	`{`
`1254`	`1254`	`"cell_type": "code",`
`1255`		`- "execution_count": 54,`
	`1255`	`+ "execution_count": 26,`
`1256`	`1256`	`"metadata": {},`
`1257`	`1257`	`"outputs": [`
`1258`	`1258`	`{`
`@@ -1346,7 +1346,7 @@`
`1346`	`1346`	`"init gpt-4o init False 57.17 ± 12.10 "`
`1347`	`1347`	`]`
`1348`	`1348`	`},`
`1349`		`- "execution_count": 54,`
	`1349`	`+ "execution_count": 26,`
`1350`	`1350`	`"metadata": {},`
`1351`	`1351`	`"output_type": "execute_result"`
`1352`	`1352`	`}`